EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Large Language Model Challenges to Detect Cancer-Related Cognitive Impairment from Patient Short Speech

Sofia Gaiduchenko, Eiji Aramaki, Seiji Shimidzu, Takako Fujimaki, Kyoko Kawabata, Shoko Wakamiya, Mizuki Shimadzu Kato, Isao Miyashiro

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti251214 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Sofia Gaiduchenko und 7 weiteren Autor:innen. Beteiligte Einrichtung: Nara Institute of Science and Technology (NAIST), Nara, Japan. Hauptthemen laut MEDLINE: Natural Language Processing, Cognitive Dysfunction, Neoplasms. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study uses language-based Cancer-Related Cognitive Impairment (CRCI) screening to examine the language ability of the participants. This study was conducted to determine whether a natural language processing-based system can detect CRCI or not. We obtained speech samples from participants including patients with cancer and cognitive impairment scores. Using LLMs, we extracted 8 linguistic measurement metrics from the collected data. We divided patients into high-cognitive and low-cognitive) groups. The results did not show any correlation between CRCI and language features derived from participants’ speech using LLMs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingCognitive DysfunctionNeoplasmsHumansFemaleMaleMiddle AgedAgedLarge Language Models

Stichwörter der Autor:innen

CancerCognitive DysfunctionLarge Language Model (LLM)Natural Language Processing (NLP)

Autor:innen und Institutionen

  • Nara Institute of Science and Technology (NAIST), Nara, Japan.
  • Osaka International Cancer Institute (OICI), Osaka, Japan.

Zitieren

APA

Gaiduchenko, S., Aramaki, E., Shimidzu, S., Fujimaki, T., Kawabata, K., Wakamiya, S., Shimadzu Kato, M., & Miyashiro, I. (2025). Large Language Model Challenges to Detect Cancer-Related Cognitive Impairment from Patient Short Speech. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251214

Vancouver

Gaiduchenko S, Aramaki E, Shimidzu S, Fujimaki T, Kawabata K, Wakamiya S, et al. Large Language Model Challenges to Detect Cancer-Related Cognitive Impairment from Patient Short Speech. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251214

BibTeX
@article{Gaiduchenko2025,
  author = {Gaiduchenko, Sofia and Aramaki, Eiji and Shimidzu, Seiji and Fujimaki, Takako and Kawabata, Kyoko and Wakamiya, Shoko and Shimadzu Kato, Mizuki and Miyashiro, Isao},
  title = {Large Language Model Challenges to Detect Cancer-Related Cognitive Impairment from Patient Short Speech},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti251214}
}
Kostenlos starten →